AN EXTENSIVE INVESTIGATION ABOUT THE DEVELOPMENTS OF LEARNING ALGORITHMS FOR FOREST FIRE PREDICTION AND TRACKING

Abstract

Forest fires, which cause significant harm to both the environment and the economy, are becoming more frequent worldwide. This underscores the urgent need for early prediction and detection. Various technologies and techniques have been proposed to anticipate and detect forest fires, with artificial intelligence emerging as a critical enabler. Specifically, machine learning (ML) techniques have garnered considerable interest for their potential in predicting and assessing the risk of forest fire-induced damage. This article reviews the machine learning methods used for identifying and forecasting forest fires. Choosing the optimal forecasting model remains a challenge, as each ML algorithm has its own strengths and weaknesses. Our primary objective is to identify research gaps and recent studies that leverage machine learning techniques in the study of forest fires. By selecting the most suitable ML techniques based on specific forest characteristics, current research enhances predictive accuracy.